Skip to main content

01-04-2013 | Lung cancer | Article

Modified prediction model may improve lung cancer detection


Free abstract

medwireNews: A modified lung cancer prediction model that includes risk factors identified in the National Lung Screening Trial (NLST) may boost the accuracy with which 6-year lung cancer risk can be predicted, researchers report.

The prediction model (PLCOM2012) is a modified version of the 2011 lung-cancer risk-prediction model from the Prostate, Lung, Colorectal, and Ovarian (PLCO) Cancer Screening Trial, with the NLST criteria a smoking history of at least 30 pack-years and less than 15 years since smoking cessation added.

When compared with NLST criteria, the PLCOM2012had a better predictive sensitivity for predicting lung cancer among smokers, at 83.0% versus 71.1%.

As reported in the New England Journal of Medicine, when used among individuals aged 55 to 74 years and with no history of lung cancer, PLCOM2012 had a better positive predictive value than NLST criteria alone, at 4.0% and 3.4%, respectively.

In all, 41.3% fewer lung cancers were missed with use of the modified model compared with use of NLST criteria alone, say Martin Tammemägi (Brock University, Ontario, Canada) and team.

They add: "The wide gap in the ability to predict lung cancers between the NLST and PLCOM2012 criteria should translate into more efficient selection for screening (a higher number of cancers detected per number of persons screened), greater cost-effectiveness, and additional lives saved from low-dose computed tomography screening."

Factors used in the original PLCO model included patient age, level of education, body-mass index (BMI), family history of lung cancer, chronic obstructive pulmonary disease (COPD), chest X-ray in the previous 3 years, smoking status, and history of cigarette smoking in pack-years.

Tammemägi and colleagues found that 14,144 (37.9%) of 37,332 smokers from the 2011 PLCO cancer screening trial intervention group (those who received chest X-ray) met NLST criteria.

To compare the lung cancer predictive accuracy of NLST criteria with PLCOM2012, the researchers selected another 14,144 individuals considered eligible for screening according to PLCOM2012 criteria from the 80,375 current or former smokers included in the PLCO trial.

The discriminative ability of each model was assessed using a receiver-operating-characteristic curve.

The PLCOM2012 model identified that lung cancer risk was positively associated with age, Black ethnicity (compared with White ethnicity), self-reported history of chronic obstructive pulmonary disease, history of cancer, family history of cancer, and smoking intensity.

It also revealed an inverse association between lung cancer risk and socioeconomic status (determined according to the level of education) and BMI.

Tammemägi and co-authors conclude: "In both the PLCO and the NLST, an age between 55 and 74 years was an entry criterion. Therefore, the predictive performance of the PLCOM2012 outside this age range is uncertain, although most lung cancers occur in persons in this age range."

medwireNews ( is an independent clinical news service provided by Springer Healthcare Limited. © Springer Healthcare Ltd; 2013

By Lauretta Ihonor, medwireNews reporter

Related topics

See the research in context now

with trial summaries, expert opinion and congress coverage